Create app.py

app.py

@@ -0,0 +1,71 @@
+import os
+import streamlit as st
+import fitz
+import openai
+import sqlite3
+from langchain.embeddings import OpenAIEmbeddings
+from langchain.vectorstores import FAISS
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+import pdfplumber
+
+# Initialize once
+@st.cache_resource
+def init_system():
+    # 1. Process PDF
+    process_pdf("Q1FY24.pdf")
+    
+    # 2. Load pre-processed data
+    embeddings = OpenAIEmbeddings(openai_api_key=os.getenv("OPENAI_API_KEY"))
+    vector_store = FAISS.load_local("faiss_index", embeddings)
+    
+    # 3. Connect SQL
+    conn = sqlite3.connect('metric_table.db')
+    return vector_store, conn
+
+def process_pdf(pdf_path):
+    # Structured Data
+    conn = sqlite3.connect('metric_table.db')
+    cursor = conn.cursor()
+    cursor.execute('''CREATE TABLE IF NOT EXISTS metric_table 
+                    (metric TEXT, quarter TEXT, value REAL)''')
+
+    # Unstructured Data
+    full_text = ""
+    doc = fitz.open(pdf_path)
+    
+    with pdfplumber.open(pdf_path) as pdf:
+        for page_num, page in enumerate(pdf.pages):
+            # Structured extraction
+            if "Financial Performance Summary" in page.extract_text():
+                tables = page.extract_tables()
+                # Add to SQL (example)
+
+    # ... (Add full processing logic from previous code)
+
+    # Save vector store
+    splitter = RecursiveCharacterTextSplitter(chunk_size=1000)
+    chunks = splitter.split_text(full_text)
+    embeddings = OpenAIEmbeddings(openai_api_key=os.getenv("OPENAI_API_KEY"))
+    FAISS.from_texts(chunks, embeddings).save_local("faiss_index")
+
+# Streamlit UI
+def main():
+    st.title("Fundrev Financial Analyzer")
+    
+    # Initialize system
+    vector_store, conn = init_system()
+    
+    query = st.text_input("Ask financial question:")
+    
+    if query:
+        # Hybrid query logic
+        if any(keyword in query.lower() for keyword in ["trend", "margin", "growth"]):
+            cursor = conn.cursor()
+            cursor.execute(f"SELECT * FROM metric_table WHERE metric LIKE '%{query}%'")
+            st.table(cursor.fetchall())
+        else:
+            docs = vector_store.similarity_search(query)
+            st.write(docs[0].page_content)
+
+if __name__ == "__main__":
+    main()